deepseek-ai/DeepSeek-VL2
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-VL2.git synced 2026-11-05 01:07:23 +00:00
Code Issues 123 Projects Packages Wiki Activity

[GH-ISSUE #27] DeepseekVLV2Processor missing 3 required positional arguments #24

New issue
Open
opened 2026-10-26 21:10:22 +00:00 by bsakaguchi · 3 comments
bsakaguchi commented 2026-10-26 21:10:22 +00:00
Owner
Copy link

Originally created by @CHIzhP on GitHub (Dec 28, 2024).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-VL2/issues/27

Hi!

I'm using the demo codes to run deepseek-vl2-small:

model_path = "deepseek-ai/deepseek-vl2-small"
vl_chat_processor: DeepseekVLV2Processor = DeepseekVLV2Processor.from_pretrained(model_path)
tokenizer = vl_chat_processor.tokenizer

And here's an error:
TypeError: DeepseekVLV2Processor.init() missing 3 required positional arguments: 'candidate_resolutions', 'patch_size', and 'downsample_ratio

I wonder if there are any default or suggested values for them. Thanks a lot!

Originally created by @CHIzhP on GitHub (Dec 28, 2024). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-VL2/issues/27 Hi! I'm using the demo codes to run `deepseek-vl2-small`: ``` model_path = "deepseek-ai/deepseek-vl2-small" vl_chat_processor: DeepseekVLV2Processor = DeepseekVLV2Processor.from_pretrained(model_path) tokenizer = vl_chat_processor.tokenizer ``` And here's an error: TypeError: DeepseekVLV2Processor.__init__() missing 3 required positional arguments: 'candidate_resolutions', 'patch_size', and 'downsample_ratio I wonder if there are any default or suggested values for them. Thanks a lot!
bsakaguchi commented 2026-10-26 21:10:23 +00:00
Author
Owner
Copy link

@Owuau12 commented on GitHub (Feb 1, 2025):

model_path = "deepseek-ai/deepseek-vl2-small"
vl_chat_processor: DeepseekVLV2Processor = DeepseekVLV2Processor.from_pretrained(model_path)
tokenizer = vl_chat_processor.tokenizer

<!-- gh-comment-id:2628770633 --> @Owuau12 commented on GitHub (Feb 1, 2025): model_path = "deepseek-ai/deepseek-vl2-small" vl_chat_processor: DeepseekVLV2Processor = DeepseekVLV2Processor.from_pretrained(model_path) tokenizer = vl_chat_processor.tokenizer
bsakaguchi commented 2026-10-26 21:10:24 +00:00
Author
Owner
Copy link

@qianyue76 commented on GitHub (Feb 17, 2025):

Check if the process_config.json is downloaded

<!-- gh-comment-id:2662370226 --> @qianyue76 commented on GitHub (Feb 17, 2025): Check if the process_config.json is downloaded
bsakaguchi commented 2026-10-26 21:10:24 +00:00
Author
Owner
Copy link

@NaMoCv commented on GitHub (Apr 16, 2025):

解决了吗？但我是使用vLLM部署出的这个问题。

<!-- gh-comment-id:2810049891 --> @NaMoCv commented on GitHub (Apr 16, 2025): 解决了吗？但我是使用vLLM部署出的这个问题。
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
No results found.
Labels
Clear labels   
pull-request
Mirrored from GitHub Pull Request

No labels
pull-request
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
deepseek-ai/DeepSeek-VL2#24
No description provided.